Mistral AI Provider

Learn how to use Mistral AI models for text generation and embeddings with the AI SDK.

Mistral AI Provider

The Mistral AI provider enables you to use Mistral’s language models for text generation, function calling, and embeddings.

Installation

npm

npm install @ai-sdk/mistral

pnpm add @ai-sdk/mistral

yarn add @ai-sdk/mistral

bun add @ai-sdk/mistral

Setup

Get your API key from Mistral AI Console and set it as an environment variable:

MISTRAL_API_KEY=your-api-key

Usage

Basic Text Generation

import { mistral } from '@ai-sdk/mistral';
import { generateText } from 'ai';

const { text } = await generateText({
  model: mistral('mistral-large-latest'),
  prompt: 'Explain quantum computing.',
});

Streaming Responses

import { mistral } from '@ai-sdk/mistral';
import { streamText } from 'ai';

const result = streamText({
  model: mistral('mistral-large-latest'),
  prompt: 'Write about machine learning.',
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Structured Output

import { mistral } from '@ai-sdk/mistral';
import { generateObject } from 'ai';
import { z } from 'zod';

const { object } = await generateObject({
  model: mistral('mistral-large-latest'),
  schema: z.object({
    topics: z.array(z.string()),
    difficulty: z.enum(['beginner', 'intermediate', 'advanced']),
  }),
  prompt: 'Categorize this content.',
});

Configuration

Custom Provider Instance

import { createMistral } from '@ai-sdk/mistral';

const mistral = createMistral({
  apiKey: process.env.MISTRAL_API_KEY,
  baseURL: 'https://api.mistral.ai/v1',
});

Provider Options

• apiKey: Your Mistral API key (defaults to MISTRAL_API_KEY env var)
• baseURL: Custom API endpoint URL
• headers: Custom headers for requests

Available Models

Text Models

• mistral-large-latest - Most capable model
• mistral-medium-latest - Balanced performance
• mistral-small-latest - Fast and efficient
• pixtral-large-latest - Multimodal model with vision

Reasoning Models

• magistral-small-2507 - Reasoning model
• magistral-medium-2507 - Advanced reasoning

Advanced Features

Tool Calling

import { mistral } from '@ai-sdk/mistral';
import { generateText } from 'ai';
import { z } from 'zod';

const result = await generateText({
  model: mistral('mistral-large-latest'),
  tools: {
    get_weather: {
      description: 'Get weather information',
      parameters: z.object({
        city: z.string(),
      }),
      execute: async ({ city }) => {
        return { temperature: 72, condition: 'sunny' };
      },
    },
  },
  prompt: 'What is the weather in Paris?',
});

Vision (Pixtral)

import { mistral } from '@ai-sdk/mistral';
import { generateText } from 'ai';
import fs from 'fs';

const result = await generateText({
  model: mistral('pixtral-large-latest'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What is in this image?' },
        { type: 'image', image: fs.readFileSync('./image.jpg') },
      ],
    },
  ],
});

PDF Support

import { mistral } from '@ai-sdk/mistral';
import { generateText } from 'ai';
import fs from 'fs';

const result = await generateText({
  model: mistral('mistral-small-latest'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'Summarize this PDF.' },
        {
          type: 'file',
          data: fs.readFileSync('./document.pdf'),
          mediaType: 'application/pdf',
        },
      ],
    },
  ],
  providerOptions: {
    mistral: {
      documentImageLimit: 8,
      documentPageLimit: 64,
    },
  },
});

Reasoning Models

import { mistral } from '@ai-sdk/mistral';
import { generateText } from 'ai';

const { text, reasoningText } = await generateText({
  model: mistral('magistral-small-2507'),
  prompt: 'What is 15 * 24?',
});

console.log('Reasoning:', reasoningText);
console.log('Answer:', text);

Embeddings

import { mistral } from '@ai-sdk/mistral';
import { embed } from 'ai';

const { embedding } = await embed({
  model: mistral.embedding('mistral-embed'),
  value: 'Text to embed',
});

Available Models:

• mistral-embed (1024 dimensions)

Model Capabilities

Model	Vision	Tools	Structured Output
mistral-large-latest	✗	✓	✓
mistral-medium-latest	✗	✓	✓
mistral-small-latest	✗	✓	✓
pixtral-large-latest	✓	✓	✓
magistral-small-2507	✗	✓	✓

Resources

• Mistral AI Documentation
• AI SDK Documentation
• Mistral API Reference